For the Ethernet RQs, if there all receiving descriptors are
exhausted, the packets being received will be dropped. This behavior
prevents slow or malicious software entities at the host from
affecting the network. While for hairpin cases, even if there is no
software involved during the packet forwarding from Rx to Tx side,
some hiccup in the hardware or back pressure from Tx side may still
cause the descriptors to be exhausted. In certain scenarios it may be
preferred to configure the device to avoid such packet drops,
assuming the posting of descriptors will resume shortly.
To support this, a new devarg "delay_drop" is introduced. By default,
the delay drop is enabled for hairpin Rx queues and disabled for
standard Rx queues. This value is used as a bit mask:
- bit 0: enablement of standard Rx queue
- bit 1: enablement of hairpin Rx queue
And this attribute will be applied to all Rx queues of a device.
The "rq_delay_drop" capability in the HCA_CAP is checked before
creating any queue. If the hardware capabilities do not support
this delay drop, all the Rx queues will still be created without
this attribute, and the devarg setting will be ignored even if it
is specified explicitly. A warning log is used to notify the
application when this occurs.
Signed-off-by: Bing Zhao <bingz@nvidia.com>
Acked-by: Viacheslav Ovsiienko <viacheslavo@nvidia.com>
---
doc/guides/nics/mlx5.rst | 11 +++++++++++
doc/guides/rel_notes/release_21_11.rst | 1 +
drivers/common/mlx5/mlx5_devx_cmds.c | 1 +
drivers/common/mlx5/mlx5_devx_cmds.h | 1 +
drivers/net/mlx5/linux/mlx5_os.c | 11 +++++++++++
drivers/net/mlx5/mlx5.c | 7 +++++++
drivers/net/mlx5/mlx5.h | 9 +++++++++
drivers/net/mlx5/mlx5_devx.c | 5 +++++
drivers/net/mlx5/mlx5_rx.h | 1 +
9 files changed, 47 insertions(+)
@@ -114,6 +114,7 @@ Features
- Sub-Function representors.
- Sub-Function.
- Shared Rx queue.
+- Rx queue delay drop.
Limitations
@@ -608,6 +609,16 @@ Driver options
- POWER8 and ARMv8 with ConnectX-4 Lx, ConnectX-5, ConnectX-6, ConnectX-6 Dx,
ConnectX-6 Lx, BlueField and BlueField-2.
+- ``delay_drop`` parameter [int]
+
+ Bitmask value for the Rx queue delay drop attribute. Bit 0 is used for the
+ standard Rx queue and bit 1 is used for the hairpin Rx queue. By default, the
+ delay drop is disabled for all Rx queues. It will be ignored if the port does
+ not support the attribute even if it is enabled explicitly.
+
+ The packets being received will not be dropped immediately when the WQEs are
+ exhausted in a Rx queue with delay drop enabled.
+
- ``mprq_en`` parameter [int]
A nonzero value enables configuring Multi-Packet Rx queues. Rx queue is
@@ -192,6 +192,7 @@ New Features
* Added implicit mempool registration to avoid data path hiccups (opt-out).
* Added NIC offloads for the PMD on Windows (TSO, VLAN strip, CRC keep).
* Added socket direct mode bonding support.
+ * Added delay drop support for Rx queue.
* **Updated Solarflare network PMD.**
@@ -965,6 +965,7 @@ mlx5_devx_cmd_query_hca_attr(void *ctx,
attr->ct_offload = !!(MLX5_GET64(cmd_hca_cap, hcattr,
general_obj_types) &
MLX5_GENERAL_OBJ_TYPES_CAP_CONN_TRACK_OFFLOAD);
+ attr->rq_delay_drop = MLX5_GET(cmd_hca_cap, hcattr, rq_delay_drop);
if (attr->qos.sup) {
hcattr = mlx5_devx_get_hca_cap(ctx, in, out, &rc,
MLX5_GET_HCA_CAP_OP_MOD_QOS_CAP |
@@ -178,6 +178,7 @@ struct mlx5_hca_attr {
uint32_t swp_csum:1;
uint32_t swp_lso:1;
uint32_t lro_max_msg_sz_mode:2;
+ uint32_t rq_delay_drop:1;
uint32_t lro_timer_supported_periods[MLX5_LRO_NUM_SUPP_PERIODS];
uint16_t lro_min_mss_size;
uint32_t flex_parser_protocols;
@@ -1508,6 +1508,15 @@ mlx5_dev_spawn(struct rte_device *dpdk_dev,
goto error;
#endif
}
+ if (config->std_delay_drop || config->hp_delay_drop) {
+ if (!config->hca_attr.rq_delay_drop) {
+ config->std_delay_drop = 0;
+ config->hp_delay_drop = 0;
+ DRV_LOG(WARNING,
+ "dev_port-%u: Rxq delay drop is not supported",
+ priv->dev_port);
+ }
+ }
if (sh->devx) {
uint32_t reg[MLX5_ST_SZ_DW(register_mtutc)];
@@ -2077,6 +2086,8 @@ mlx5_os_config_default(struct mlx5_dev_config *config)
config->decap_en = 1;
config->log_hp_size = MLX5_ARG_UNSET;
config->allow_duplicate_pattern = 1;
+ config->std_delay_drop = 0;
+ config->hp_delay_drop = 0;
}
/**
@@ -183,6 +183,9 @@
/* Device parameter to configure implicit registration of mempool memory. */
#define MLX5_MR_MEMPOOL_REG_EN "mr_mempool_reg_en"
+/* Device parameter to configure the delay drop when creating Rxqs. */
+#define MLX5_DELAY_DROP "delay_drop"
+
/* Shared memory between primary and secondary processes. */
struct mlx5_shared_data *mlx5_shared_data;
@@ -2091,6 +2094,9 @@ mlx5_args_check(const char *key, const char *val, void *opaque)
config->decap_en = !!tmp;
} else if (strcmp(MLX5_ALLOW_DUPLICATE_PATTERN, key) == 0) {
config->allow_duplicate_pattern = !!tmp;
+ } else if (strcmp(MLX5_DELAY_DROP, key) == 0) {
+ config->std_delay_drop = tmp & MLX5_DELAY_DROP_STANDARD;
+ config->hp_delay_drop = tmp & MLX5_DELAY_DROP_HAIRPIN;
} else {
DRV_LOG(WARNING, "%s: unknown parameter", key);
rte_errno = EINVAL;
@@ -2153,6 +2159,7 @@ mlx5_args(struct mlx5_dev_config *config, struct rte_devargs *devargs)
MLX5_DECAP_EN,
MLX5_ALLOW_DUPLICATE_PATTERN,
MLX5_MR_MEMPOOL_REG_EN,
+ MLX5_DELAY_DROP,
NULL,
};
struct rte_kvargs *kvlist;
@@ -99,6 +99,13 @@ enum mlx5_flow_type {
MLX5_FLOW_TYPE_MAXI,
};
+/* The mode of delay drop for Rx queues. */
+enum mlx5_delay_drop_mode {
+ MLX5_DELAY_DROP_NONE = 0, /* All disabled. */
+ MLX5_DELAY_DROP_STANDARD = RTE_BIT32(0), /* Standard queues enable. */
+ MLX5_DELAY_DROP_HAIRPIN = RTE_BIT32(1), /* Hairpin queues enable. */
+};
+
/* Hlist and list callback context. */
struct mlx5_flow_cb_ctx {
struct rte_eth_dev *dev;
@@ -264,6 +271,8 @@ struct mlx5_dev_config {
unsigned int dv_miss_info:1; /* restore packet after partial hw miss */
unsigned int allow_duplicate_pattern:1;
/* Allow/Prevent the duplicate rules pattern. */
+ unsigned int std_delay_drop:1; /* Enable standard Rxq delay drop. */
+ unsigned int hp_delay_drop:1; /* Enable hairpin Rxq delay drop. */
struct {
unsigned int enabled:1; /* Whether MPRQ is enabled. */
unsigned int stride_num_n; /* Number of strides. */
@@ -277,6 +277,7 @@ mlx5_rxq_create_devx_rq_resources(struct mlx5_rxq_priv *rxq)
MLX5_WQ_END_PAD_MODE_NONE;
rq_attr.wq_attr.pd = cdev->pdn;
rq_attr.counter_set_id = priv->counter_set_id;
+ rq_attr.delay_drop_en = rxq_data->delay_drop;
rq_attr.user_index = rte_cpu_to_be_16(priv->dev_data->port_id);
if (rxq_data->shared) /* Create RMP based RQ. */
rxq->devx_rq.rmp = &rxq_ctrl->obj->devx_rmp;
@@ -439,6 +440,8 @@ mlx5_rxq_obj_hairpin_new(struct mlx5_rxq_priv *rxq)
attr.wq_attr.log_hairpin_data_sz -
MLX5_HAIRPIN_QUEUE_STRIDE;
attr.counter_set_id = priv->counter_set_id;
+ rxq_ctrl->rxq.delay_drop = priv->config.hp_delay_drop;
+ attr.delay_drop_en = priv->config.hp_delay_drop;
tmpl->rq = mlx5_devx_cmd_create_rq(priv->sh->cdev->ctx, &attr,
rxq_ctrl->socket);
if (!tmpl->rq) {
@@ -496,6 +499,7 @@ mlx5_rxq_devx_obj_new(struct mlx5_rxq_priv *rxq)
DRV_LOG(ERR, "Failed to create CQ.");
goto error;
}
+ rxq_data->delay_drop = priv->config.std_delay_drop;
/* Create RQ using DevX API. */
ret = mlx5_rxq_create_devx_rq_resources(rxq);
if (ret) {
@@ -941,6 +945,7 @@ mlx5_rxq_devx_obj_drop_create(struct rte_eth_dev *dev)
dev->data->port_id);
goto error;
}
+ rxq_ctrl->rxq.delay_drop = 0;
/* Create RQ using DevX API. */
ret = mlx5_rxq_create_devx_rq_resources(rxq);
if (ret != 0) {
@@ -97,6 +97,7 @@ struct mlx5_rxq_data {
unsigned int dynf_meta:1; /* Dynamic metadata is configured. */
unsigned int mcqe_format:3; /* CQE compression format. */
unsigned int shared:1; /* Shared RXQ. */
+ unsigned int delay_drop:1; /* Enable delay drop. */
volatile uint32_t *rq_db;
volatile uint32_t *cq_db;
uint16_t port_id;